INTELLIGENCE
45.6
Media Cap quality axis
DeepSeek · Open weightsDeepSeek: DeepSeek V4 Flash 0423
Active
Model portfolio
DeepSeek: DeepSeek V4 Flash 0423
Tap a star to rate
DeepSeek · Released 2026-07-31 · v2026-07-31 · Open · Context 1.0M tokens
Language Cap
79
Cadle Language Cap 79 · 79%
Benchmark average
79.4
Not enough benchmark results yet
Pricing
$0.091
$0.18 / 1M out · 308.2 pts/$
CADLE CAP vs MODEL MATRIX
Cadle Cap ranks models on every published score we have for them — harder benchmarks weigh more. Missing tests are skipped, not zeroed. It answers who is stronger than whom in today's pool.
Model Matrix is the datasheet: Overall, Intelligence, Coding, Agentic, MMLU, GPQA, Math, LiveCodeBench, HumanEval, Reason, ARC-AGI. A dash means unmeasured. AVG is an importance-weighted mean of that model's filled cells only.
MODEL MATRIX · TRUTH CENTER CELLS
Overall
66.0
Intelligence
34.3
Coding
71.2
Agentic
78.7
MMLU
No data yet
GPQA
90.8
Math
97.1
LiveCodeBench
50.3
HumanEval
No data yet
Reason
98.0
ARC-AGI
No data yet
Coverage AVG
79.4
Cadle Cap ranks models with within-benchmark percentiles so ARC-AGI ~40 and MMLU ~90 never compete raw. Coverage AVG is an importance-weighted mean of filled expert cells only — blanks are skipped, not zeroed.
ANALYSIS · TRUTH CENTER
Hard benches (GPQA · ARC-AGI · LCB · Agentic) sit left — a mid-40 on ARC-AGI can still be frontier. Broader benches on the right are easier and often higher.
CADLE INSIGHTS
Only measured signals
CODING
71.2
Media Cap quality axis
AGENTIC
78.7
Media Cap quality axis
MATH
97.1
Media Cap quality axis
MATRIX OVERALL
66.0
AVG 79.4 across matrix cells
STRONGEST SIGNAL
Intelligence
Cap axis 45.6
BLENDED $/1M
$0.27
In $0.091 · Out $0.18
VALUE INDEX
241.9
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 66.0
- Cap Intelligence
- 84.2
- AA / Intel index
- 34.3
- Cap Coding
- 68.2
- Matrix Coding
- 71.2
- Input $/1M
- $0.091
- Output $/1M
- $0.18
- Value pts/$
- 308.24
DESCRIPTION + DETAILS
PROVIDER
DeepSeek
RELEASE
2026-07-31
CONTEXT
1.0M tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate DeepSeek: DeepSeek V4 Flash 0423.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | DeepSeek |
| Release | 2026-07-31 |
| Input / 1M | $0.09 |
| Output / 1M | $0.18 |
| Context | 1.0M tokens |
| Cadle Cap | 79 |
| Cap board | Cadle Language Cap 79 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
DeepSeek listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall66
AA IQ34.3
Coding71.2
Agentic78.7
GPQA90.8
Math97.1
LiveCodeBench50.3